Update README.md
Browse files
README.md
CHANGED
|
@@ -167,16 +167,11 @@ print("model.layers[0].self_attn.q_proj.weight", model.model.layers[0].self_attn
|
|
| 167 |
print("lm_head.weight", model.lm_head.weight)
|
| 168 |
```
|
| 169 |
|
| 170 |
-
################################################################################
|
| 171 |
-
# Export to ET
|
| 172 |
-
################################################################################
|
| 173 |
-
|
| 174 |
-
|
| 175 |
# Exporting to ExecuTorch
|
| 176 |
|
| 177 |
We can run the quantized model on a mobile phone using [ExecuTorch](https://github.com/pytorch/executorch):
|
| 178 |
|
| 179 |
-
```
|
| 180 |
# 1. Install ExecuTorch
|
| 181 |
pip install executorch pytorch_tokenizers torchtune
|
| 182 |
|
|
|
|
| 167 |
print("lm_head.weight", model.lm_head.weight)
|
| 168 |
```
|
| 169 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 170 |
# Exporting to ExecuTorch
|
| 171 |
|
| 172 |
We can run the quantized model on a mobile phone using [ExecuTorch](https://github.com/pytorch/executorch):
|
| 173 |
|
| 174 |
+
```bash
|
| 175 |
# 1. Install ExecuTorch
|
| 176 |
pip install executorch pytorch_tokenizers torchtune
|
| 177 |
|